paper-with-me

홈 › Papers

Building Blocks for a Complex-Valued Transformer Architecture

2023-06-16 · Florian Eilers, Xiaoyi Jiang

Most deep learning pipelines are built on real-valued operations to deal with real-valued inputs such as images, speech or music signals. However, a lot of applications naturally make use of complex-valued signals or images, such as MRI or remote sensing. Additionally the Fourier transform of signals is complex-valued and has numerous applications. We aim to make deep learning directly applicable to these complex-valued signals without using projections into $\mathbb{R}^2$. Thus we add to the recent developments of complex-valued neural networks by presenting building blocks to transfer the transformer architecture to the complex domain. We present multiple versions of a complex-valued Scaled Dot-Product Attention mechanism as well as a complex-valued layer normalization. We test on a classification and a sequence generation task on the MusicNet dataset and show improved robustness to overfitting while maintaining on-par performance when compared to the real-valued transformer architecture.

📄 PDF Abstract BibTeX arXiv:2306.09827

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Deep Complex Networks

2017-05-27 · ICLR 2018 1 · Chiheb Trabelsi, Olexa Bilaniuk, Ying Zhang, Dmitriy Serdyuk 외

At present, the vast majority of building blocks, techniques, and architectures for deep learning are based on real-valued operations and representations. However, recent work on recurrent neural networks and older funda…

Image ClassificationMusic TranscriptionRetrieval

Hybrid Real- and Complex-valued Neural Network Architecture

2025-04-04 · Alex Young, Luan Vinícius Fiorio, Bo Yang, Boris Karanov 외

We propose a \emph{hybrid} real- and complex-valued \emph{neural network} (HNN) architecture, designed to combine the computational efficiency of real-valued processing with the ability to effectively handle complex-valu…

Computational EfficiencyNavigate

Rethinking complex-valued deep neural networks for monaural speech enhancement

2023-01-11 · Haibin Wu, Ke Tan, Buye Xu, Anurag Kumar 외

Despite multiple efforts made towards adopting complex-valued deep neural networks (DNNs), it remains an open question whether complex-valued DNNs are generally more effective than real-valued DNNs for monaural speech en…

Open-Ended Question AnsweringSpeech Enhancement

End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression

2021-10-02 · Karn N. Watcharasupat, Thi Ngoc Tho Nguyen, Woon-Seng Gan, Shengkui Zhao 외

Echo and noise suppression is an integral part of a full-duplex communication system. Many recent acoustic echo cancellation (AEC) systems rely on a separate adaptive filtering module for linear echo suppression and a ne…

Acoustic echo cancellationSpeech Enhancement

Simplifying Transformer Blocks

2023-11-03 · Bobby He, Thomas Hofmann

A simple design recipe for deep Transformers is to compose identical building blocks. But standard transformer blocks are far from simple, interweaving attention and MLP sub-blocks with skip connections & normalisation l…

Decoder